Advances in Science and Technology Vol. 105

Abstract: Sign languages display the same linguistic characteristics as oral languages and utilize the same language services. Sign language processing solutions provide a communication link for persons with hearing impairments and healthy persons. Without these icons' ability to understand, deaf children experience several challenges in learning social norms and cannot meet adults to exchange knowledge. Parents find it challenging to express their messages to their deaf children and not hear their children. This paper focused on establishing Urdu sign language to reduce the communication barrier between ordinary folks and physically impaired people. The present study observed the Urdu Sign Language in deaf children. In this paper, the process of detecting Urdu sign language alphabets is proposed. All the 37 alphabets are identified by using KNN, ANN, and SVM classifiers. Through these alphabets, the teachers at schools and the parents at home can communicate efficiently with their deaf children. Histogram of Gradient technique is used for feature extraction. Urdu Alphabetic are identified. Maximum accuracy is obtained by using a KNN classifier that was 99, which is a significant contribution. Our proposed results are comparable to the state of the art techniques.

Abstract: With the rapid development of science and technology, more and more new methods and technologies have been added to the traditional Chinese Medicine Inheritance model, which makes the process of inheritance of famous doctors have more means, and the results of inheritance are more objective, rigorous and intelligent. In the process of inheriting the informationization of famous doctors, there are some bottlenecks, such as data acquisition difficulties, data processing difficulties, algorithm application difficulties, analysis and summary difficulties. Integration of artificial intelligence with big data, deep learning algorithm and knowledge atlas technology has brought technological innovation to the informationization of famous doctors' inheritance. Under this wave, the team of the Intelligent Research and Development Center of Traditional Chinese Medicine, Institute of Traditional Chinese Medicine Information, Chinese Academy of Traditional Chinese Medical Sciences, has developed a series of professional application systems in the field of traditional Chinese medicine around the planning of famous doctors' inheritance and excavation, and has developed ancient Chinese medicine, such as Today's Medical Records Cloud Platform, Medical Records Big Data Analysis Platform, Cloud Medical Records APP, Famous Medical Heritage Workstation. To a certain extent, it can solve the problems of inefficient collection of medical records, lack of objective data support and information barriers in the summary of famous doctors' experience under the limitation of traditional model, so as to promote the inheritance of famous doctors' experience and enhance the teaching ability and efficiency of teachers and apprentices.

Abstract: In this paper, a pre-trained CNN model VGG16 with the SVM classifier is presented for the HAR task. The deep features are learned via the VGG16 pre-trained CNN model. The VGG 16 network is previously used for the image classification task. We used VGG16 for the signal classification of human activity, which is recorded by the accelerometer sensor of the mobile phone. The UniMiB dataset contains the 11771 samples of the daily life activity of humans. A Smartphone records these samples through the accelerometer sensor. The features are learned via the fifth max-pooling layer of the VGG16 CNN model and feed to the SVM classifier. The SVM classifier replaced the fully connected layer of the VGG16 model. The proposed VGG16-SVM model achieves effective and efficient results. The proposed method of VGG16-SVM is compared with the previously used schemes. The classification accuracy and F-Score are the evaluation parameters, and the proposed method provided 79.55% accuracy and 71.63% F-Score.

Abstract: With more and more malicious traffic using TLS protocol encryption, efficient identification of TLS malicious traffic has become an increasingly important task in network security management in order to ensure communication security and privacy. Most of the traditional traffic identification methods on TLS malicious encryption only adopt the common characteristics of ordinary traffic, which results in the increase of coupling among features and then the low identification accuracy. In addition, most of the previous work related to malicious traffic identification extracted features directly from the data flow without recording the extraction process, making it difficult for subsequent traceability. Therefore, this paper implements an efficient feature extraction method with structural correlation for TLS malicious encrypted traffic. The traffic feature extraction process is logged in modules, and the index is used to establish relevant information links, so as to analyse the context and facilitate subsequent feature analysis and problem traceability. Finally, Random Forest is used to realize efficient TLS malicious traffic identification with an accuracy of up to 99.38%.

Abstract: Hyperbolic functions are widely used to write solutions to ordinary differential equations and partial differential equations. These functions are nonlinear in parameters, which makes it difficult to estimate the parameters of these functions. In the paper, two-step algorithms for estimating the parameters of hyperbolic sine and cosine (sinh and cosh) in the presence of measurement errors are proposed. At the first step, the hyperbolic function is transformed into a linear difference equation (autoregression) of the second order. Estimation in the presence of noise of observation of autoregression parameters using ordinary least square (OLS) gives biased estimates. Modifications of the two-stage estimation algorithm based on the use of the method of total least squares (TLS) and the method of extended instrumental variables (EIV), hyperbolic sine and cosine in the presence of errors in measurements are proposed. Numerical experiments have shown that the accuracy of the parameter estimation using the proposed modifications is higher than the accuracy of the estimate obtained using the ordinary least squares method (OLS).

Abstract: The traditional collaborative filtering recommendation algorithm has the defects of sparse score matrix, weak scalability and user interest deviation, which lead to the low efficiency of algorithm and low accuracy of score prediction. Aiming at the above problems, this paper proposed a time-weighted collaborative filtering algorithm based on improved Mini Batch K-Means clustering. Firstly, the algorithm selected the Pearson correlation coefficient to improve the Mini Batch K-Means clustering, and used the improved Mini Batch K-Means algorithm to cluster the sparse scoring matrix, calculated the user interest score to complete the filling of the sparse matrix. Then, considering the influence of user interest drift with time, the algorithm introduced the Newton cooling time-weighted to improve user similarity. And then calculated user similarity based on the filled score matrix, which helped to get the last predicted score of unrated items The experimental results show that, compared with the traditional collaborative filtering algorithms, the mean absolute error of Proposed improved algorithm is d, and the Precision, Recall and F1 value of MBKT-CF also get a large improvement, which has a higher rating prediction accuracy.

Abstract: Coronavirus becomes cerebral pain every day throughout the world. Many cases of coronavirus continue to grow, directly irritating human daily exercises and devastating the economy of nations. The Indian Government announced a one day Janta curfew on March 22, 2020. After three days on March 25 2020, 19 days of lockdown were declared in the country for mitigation of the COVID-19 pandemic. Four lockdowns and six unlock periods were implemented to control the pandemic, but lockdown is the major obstacle to the economy. In unlocking period government open the economic activity stepwise to boost the economy. Coronavirus infection is under control during a lockdown time, but the infection becomes pandemic unlock 1.0, 2.0 and 3.0 period. In Unlock 4.0 and unlock 5.0 coronavirus cases growth goes down but in unlock period 6.0, a sudden spike in confirmed cases. It is due to the festival session and relaxation provided by the Government in the unlock 6.0. The research aimed to forecast the trend towards the COVID-19 pandemic in India with data from June 01, 2020, by applying the ARIMA and Prophet model. Based on several presumptions, the findings of the analysis have shown that, after the unlock-up period is completed, it has been predicted that India's pandemic is expected to decrease by approximately about December 2020 and that it will crest around within the initial weeks of March 2021.

Abstract: With the rapid development of communication technology, modern communication technology has been widely penetrated into modern national defense, science and technology, people's life and other fields, and has become a means to provide high-quality and seamless information communication between people and machines. With the rapid development of computer technology and the Internet, the traditional program-controlled switching technology has come to an end, and the soft-switch network based on IP technology and packet switching has gradually replaced the program-controlled switching network based on circuit switching and become the mainstream of today's communication network world. The rapid development of VOIP telephony reduces the cost of domestic and international long-distance telephony, benefiting consumers. Digital mobile communication expands channel capacity, improves service quality and promotes the rapid development of this industry. Based on the secondary development of the open source FreeSWITCH software, this paper develops a VOIP voice system based on IP technology to meet different user needs intelligently [1].

Abstract: The recursive algorithm has two core issues which are the design of recursive parameter lists and exit condition. We summarized the types and characteristics of recursive algorithms, and extracted four types of representative recursive algorithms with different levels of difficulty. Pseudocodes of these algorithms are given and the core issues complexity of these algorithms is compared. The relatively complex and representative recursive algorithm of the maze path finding is described in detail. The description includes that the maze is expressed mathematically, using numbers from 0 to 9 to represent the path cost, using * to represent walls or obstacles, and abstracting the maze problem as a square maze represented by numbers and *. The maze path finding recursive algorithm has five steps which are the storage structure of the maze numbers and *, the consideration of the two core problems of the recursive algorithm, the recursive call in the four directions of the middle point and the printing of the maze path. The screenshot of the running result in C language is showed. Students are required to implement the maze path finding recursive algorithm in C language. Because the maze path finding recursive algorithm is interesting and challenging, it can stimulate students' enthusiasm and initiative in learning. In the current situation of online course teaching during the epidemic, considering the demand for C language programming ability, combining with the characteristics of higher vocational students and the difficulty of the maze path finding recursive algorithm, we designed and practiced the C Language online course teaching mode led by the recursive algorithms. The every step of the teaching mode is described in detail. From the feedback of students’ evaluation of teaching and teacher’s evaluation of learning, this teaching mode is praised by teachers and students.

Abstract: The paper proposed a practice teaching mode by making analysis on Didi data set. There are more and more universities have provided the big data analysis courses with the rapid development and wide application of big data analysis technology. The theoretical knowledge of big data analysis is professional and hard to understand. That may reduce students' interest in learning and learning motivation. And the practice teaching plays an important role between theory learning and application. This paper first introduces the theoretical teaching part of the course, and the theoretical methods involved in the course. Then the practice teaching content of Didi data analysis case was briefly described. And the study selects the related evaluation index to evaluate the teaching effect through questionnaire survey and verify the effectiveness of teaching method. The results show that 78% of students think that practical teaching can greatly improve students' interest in learning, 89% of students think that practical teaching can help them learn theoretical knowledge, 89% of students have basically mastered the method of big data analysis technology introduced in the course, 90% of students think that the teaching method proposed in this paper can greatly improve students' practical ability. The teaching mode is effective, which can improve the learning effect and practical ability of students in data analysis, so as to improve the teaching effect.